AndresFreundTec on Nostr: My best theory so far is that somehow on that one core there are more conflicts on ...
My best theory so far is that somehow on that one core there are more conflicts on L1i entries, leader to a lower hit rate. I haven't figured out what the precise keying scheme for the L1i is (it's 8 way associative).
Published at
2024-05-26 10:03:36Event JSON
{
"id": "ac5a936d52bf7cd2e0004b0f67d540a3124f1269db7f24d6510a4cc93bb459ee",
"pubkey": "f92b50f90934c1b547d709b076927c834559258b00ef49ed037607035b62a4f4",
"created_at": 1716717816,
"kind": 1,
"tags": [
[
"e",
"7dcc65093d18540f1274a8ea1343d92832f56bb3e163226e40f4c27fec116f83",
"wss://relay.mostr.pub",
"reply"
],
[
"proxy",
"https://mastodon.social/users/AndresFreundTec/statuses/112506818791536815",
"activitypub"
]
],
"content": "My best theory so far is that somehow on that one core there are more conflicts on L1i entries, leader to a lower hit rate. I haven't figured out what the precise keying scheme for the L1i is (it's 8 way associative).",
"sig": "b3540f384dc5cf46e7c0ddc420182b47788d869d5b42e267c829673fdd1c4ced06fbd3ab7dfb671acb6f8a1677c4ecd27925b01dbcf4a8353992310c69ffe9d5"
}
